Publications related to Temporal difference learning

Surprise-based model estimation in reinforcement learning: algorithms and brain signatures

Learning how to act and adapting to unexpected changes are remarkable capabilities of humans and other animals. In the absence of a direct recipe to follow in life, behaviour is often guided by rewarding and by surprising events. A positive or a negative o ...

EPFL2021

From Learning to Memory: A Comparison Between Verbal and Non-verbal Skills in 22q11.2 Deletion Syndrome

Maude Schneider, Karin Bortolin

Background: Previous studies on possible memory deficits in 22q11DS often focused on quantifying the information memorized, whereas learning processes have been mostly overlooked. Furthermore, methodological differences in task design have made verbal and ...

FRONTIERS MEDIA SA2021

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

Martin Jaggi, Sebastian Urban Stich, Amirkeivan Mohtashami

It has been experimentally observed that the efficiency of distributed training with stochastic gradient (SGD) depends decisively on the batch size and—in asynchronous implementations—on the gradient staleness. Especially, it has been observed that the spe ...

2021

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

Sabine Süsstrunk, Mathieu Salzmann, Tao Lin, Chen Liu

We analyze the influence of adversarial training on the loss landscape of machine learning models. To this end, we first provide analytical studies of the properties of adversarial loss functions under different adversarial budgets. We then demonstrate tha ...

2021

Improving Multi-agent Coordination by Learning to Estimate Contention

Boi Faltings, Panayiotis Danassis, Florian Wiedemair

We present a multi-agent learning algorithm, ALMA-Learning, for efficient and fair allocations in large-scale systems. We circumvent the traditional pitfalls of multi-agent learning (e.g., the moving target problem, the curse of dimensionality, or the need ...

2021

Improving Multi-agent Coordination by Learning to Estimate Contention

Boi Faltings, Panayiotis Danassis, Florian Wiedemair

We present a multi-agent learning algorithm, ALMA-Learning, for efficient and fair allocations in large-scale systems. We circumvent the traditional pitfalls of multi-agent learning (e.g., the moving target problem, the curse of dimensionality, or the need ...

2021

Determining 1D fast-ion velocity distribution functions from ion cyclotron emission data using deep neural networks

Ambrogio Fasoli, Marcelo Baquero Ruiz

The relationship between simulated ion cyclotron emission (ICE) signals s and the corresponding 1D velocity distribution function f(upsilon(perpendicular to)) of the fast ions triggering the ICE is modeled using a two-layer deep neural network. The network ...

AIP Publishing2021

Learning the Globally Optimal Distributed LQ Regulator

Maryam Kamgarpour, Luca Furieri

We study model-free learning methods for the output-feedback Linear Quadratic (LQ) control problem in finite-horizon subject to subspace constraints on the control policy. Subspace constraints naturally arise in the field of distributed control and present ...

PMLR2020

Age-Dependent Statistical Learning Trajectories Reveal Differences in Information Weighting

Steffen Alexander Herff

Statistical learning (SL) is the ability to generate predictions based on probabilistic dependencies in the environment, an ability that is present throughout life. The effect of aging on SL is still unclear. Here, we explore statistical learning in health ...

AMER PSYCHOLOGICAL ASSOC2020

Deep Neural Networks With Trainable Activations and Controlled Lipschitz Constant

Michaël Unser, Shayan Aziznejad, Harshit Gupta, Joaquim Gonçalves Garcia Barreto Campos

We introduce a variational framework to learn the activation functions of deep neural networks. Our aim is to increase the capacity of the network while controlling an upper-bound of the actual Lipschitz constant of the input-output relation. To that end, ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

Temporal difference learning

Surprise-based model estimation in reinforcement learning: algorithms and brain signatures

From Learning to Memory: A Comparison Between Verbal and Non-verbal Skills in 22q11.2 Deletion Syndrome

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

Improving Multi-agent Coordination by Learning to Estimate Contention

Improving Multi-agent Coordination by Learning to Estimate Contention

Determining 1D fast-ion velocity distribution functions from ion cyclotron emission data using deep neural networks

Learning the Globally Optimal Distributed LQ Regulator

Age-Dependent Statistical Learning Trajectories Reveal Differences in Information Weighting

Deep Neural Networks With Trainable Activations and Controlled Lipschitz Constant

Graph Chatbot

Chat with Graph Search

Surprise-based model estimation in reinforcement learning: algorithms and brain signatures

From Learning to Memory: A Comparison Between Verbal and Non-verbal Skills in 22q11.2 Deletion Syndrome

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

Improving Multi-agent Coordination by Learning to Estimate Contention

Age-Dependent Statistical Learning Trajectories Reveal Differences in Information Weighting

Determining 1D fast-ion velocity distribution functions from ion cyclotron emission data using deep neural networks

Improving Multi-agent Coordination by Learning to Estimate Contention

Learning the Globally Optimal Distributed LQ Regulator

Deep Neural Networks With Trainable Activations and Controlled Lipschitz Constant